Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Clustering Applications:Customer Usage Archetypes
June 2019Brian Smith
Data Engineer & AnalystElectric Power Board of Chattanooga, TN
Who is EPB?
Customer Load Profile
• 15-minute meter reads• Average at each interval to get ‘typical day’, i.e. average kwh
between 1:00 and 1:15 AM, between 1:15 and 1:30 AM, etc.
Clustering Overview
Clustering Overview
Mass Clustering Customer Load Profiles
Mass Clustering Customer Load Profiles
Mass Clustering Customer Load Profiles
Mass Clustering Customer Load Profiles
Mass Clustering Customer Load Profiles
Mass Clustering Customer Load Profiles
Implications and PossibilitiesResidential – Peak Shaving
Hour of Day
kWh
Adju
sted
Implications and PossibilitiesResidential – Customer Insights
Implications and PossibilitiesResidential – Customer Insights
“Sharp Peakers” “Round Peakers”
“Night Owls”
Implications and PossibilitiesResidential – Customer Insights
Implications and PossibilitiesResidential – Customer Insights
Avg. Home Age Avg. Home Size Avg. Monthly Bill
Implications and PossibilitiesBusiness – Business Type Identification
SUN MON TUES WED THURS FRI SAT
Implications and PossibilitiesBusiness – Business Type Identification
Related Documents
